Jun Zhu

20

Papers

289

Total Citations

Papers (20)

DimensionX: Create Any 3D and 4D Scenes from a Single Image with Decoupled Video Diffusion

MeshAnything V2: Artist-Created Mesh Generation with Adjacent Mesh Tokenization

PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidance

Pruning Large Language Models with Semi-Structural Adaptive Sparse Training

Exploring the Transferability of Visual Prompting for Multimodal Large Language Models

Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator

InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image

Visual Generation Without Guidance

On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent

DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization

DUSTED: Dual-Attention Enhanced Spatial Transcriptomics Denoiser

Jetfire: Efficient and Accurate Transformer Pretraining with INT8 Data Flow and Per-Block Quantization

DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning

Robust Classification via a Single Diffusion Model

DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training

Accelerating Transformer Pre-training with 2:4 Sparsity

Towards Efficient Exact Optimization of Language Model Alignment

Fourier Controller Networks for Real-Time Decision-Making in Embodied Learning

Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior

Improving Accuracy and Calibration via Differentiated Deep Mutual Learning